decoder-only transformers 1efficient inference 1entity alignment 1knowledge graphs 1large language models 1latent reasoning 1recurrent computation 1representation learning 1structured reasoning 1zero-shot matching 1
From the 2 of 2 linked papers with an AI index.
2 papers
cs.AI2026
Penelope: Localized Latent Recurrence for Efficient Structured Reasoning
Yutong Chen, Shouqian Shi, Xinran Liu +5
Penelope introduces a method that adds a localized recurrent computation within a decoder-only Transformer to perform structured reasoning efficiently, using a latent space instead…
cs.CL2026
IRIS: Reusable Identity Representations from Frozen LLMs for Entity Alignment
Xinran Liu, Shengtao Li, Shouqian Shi +2
The paper introduces IRIS, a training-free method that uses frozen large language models to generate stable identity signatures for entities, enabling direct similarity-based align…